Awesome MCP Servers by AI Anytime

Directory / Search & discovery

WebExtract

Hosted MCP that turns a public web page into clean Markdown (page_markdown) or fixed-schema JSON with article metadata, product name/price/availability and tables (extract_url). 20 free calls/day per caller IP with no signup or key; after that a prepaid Stripe-credit Bearer key, and the REST API also takes x402 USDC on Base, Polygon, Arbitrum, Optimism, Avalanche, World Chain and Monad. Endpoint: https://api.webextract.dev/mcp · Benchmark

Live  Answered an MCP handshake without credentials and listed 2 tools.

Category
Search & discovery
Transport
http
Source
https://github.com/nyx464664816-stack/webextract
Endpoint
https://api.webextract.dev/mcp
MCP Registry
dev.webextract/extract
Reports itself as
webextract 1.1.0
Protocol
2025-06-18
Tools
2
Context cost
about 206 tokens for the tool definitions (estimated at four characters per token)
Tool definitions last changed
no change seen since first check
Handshake time
730 ms
Repository
0 stars · last push 2026-11-09 · MIT
Last checked
2026-11-22 11:27:54 UTC
Listed since
2026-11-18

Health and compatibility

Endpoint reachableVerifiedResponded in 730 ms
MCP handshake (initialize)VerifiedCompleted without credentials
Tool discovery (tools/list)Verified2 tools listed
AuthenticationVerifiedNone needed to connect
Protocol versionVerified2025-06-18
TransportVerifiedStreamable HTTP
Capabilities declaredVerifiedtools

Last checked . Verified means the check saw it happen; it says nothing about whether the server is safe.

Recent history

5 daily checks so far; median response 763 ms. Green answered, violet asked for auth, red did not answer.

Set up in your client

Claude Code

Run this in a terminal:

claude mcp add --transport http webextract https://api.webextract.dev/mcp

Claude Desktop

Open Settings → Connectors → Add custom connector and paste this URL:

https://api.webextract.dev/mcp

Or bridge it through mcp-remote in claude_desktop_config.json (needs Node.js):

{
  "mcpServers": {
    "webextract": {
      "command": "npx",
      "args": [
        "-y",
        "mcp-remote",
        "https://api.webextract.dev/mcp"
      ]
    }
  }
}

Cursor

Add to Cursor

Or add it to ~/.cursor/mcp.json (or .cursor/mcp.json in a project):

{
  "mcpServers": {
    "webextract": {
      "url": "https://api.webextract.dev/mcp"
    }
  }
}

VS Code

Add to VS Code

Or add it to .vscode/mcp.json:

{
  "servers": {
    "webextract": {
      "type": "http",
      "url": "https://api.webextract.dev/mcp"
    }
  }
}

Or from a terminal:

code --add-mcp '{"name": "webextract", "type": "http", "url": "https://api.webextract.dev/mcp"}'

Windsurf

Add it to ~/.codeium/windsurf/mcp_config.json:

{
  "mcpServers": {
    "webextract": {
      "serverUrl": "https://api.webextract.dev/mcp"
    }
  }
}

Other clients

Most clients accept this shape. The endpoint is:

https://api.webextract.dev/mcp
{
  "mcpServers": {
    "webextract": {
      "type": "http",
      "url": "https://api.webextract.dev/mcp"
    }
  }
}

If it does not connect

Tools 2

Names, descriptions and input schemas exactly as the server returned them on 2026-11-22. This is the server author's own text. Nothing is run from this page. Labels such as read-only are declared by the server and are not verified. Raw JSON

extract_urlread-onlyexternal accessFetch a public web page (robots.txt respected) and return clean Markdown plus fixed-schema JSON: article …

Fetch a public web page (robots.txt respected) and return clean Markdown plus fixed-schema JSON: article metadata, product/price, tables. HTML only, no JS execution, no PDF. Free 20 calls/day per IP; pass 'Authorization: Bearer <key>' for prepaid credits.

ParameterTypeDescription
urlstringrequiredPublic http(s) URL

Example call (required arguments only, placeholder values):

{
  "method": "tools/call",
  "params": {
    "name": "extract_url",
    "arguments": {
      "url": "..."
    }
  }
}
page_markdownread-onlyexternal accessFetch a public web page (robots.txt respected) and return clean Markdown only. HTML only, no JS execution, no …

Fetch a public web page (robots.txt respected) and return clean Markdown only. HTML only, no JS execution, no PDF. Cheaper than extract_url (0.4 credit). Free 20 calls/day per IP; pass 'Authorization: Bearer <key>' for prepaid credits.

ParameterTypeDescription
urlstringrequiredPublic http(s) URL

Example call (required arguments only, placeholder values):

{
  "method": "tools/call",
  "params": {
    "name": "page_markdown",
    "arguments": {
      "url": "..."
    }
  }
}

Badge

Maintain this server? Put its live status in your README:

MCP status badge

[![MCP status](https://mcp.aianytime.net/badge/webextract.svg)](https://mcp.aianytime.net/s/webextract/)

Edit this entry · Report a problem

More in Search & discovery

Checks record what a server answered, not whether it is safe. A listing is not a security audit; read a server's source and permissions before you connect it. Add a server · JSON · llms.txt · llms-full.txt

Browse: Agents, IDEs & developer tools · Search & discovery · Knowledge, memory & context · Media & generation · Security · Finance & markets · Marketing, content & social · Cloud, ops & data · Commerce, travel & logistics · Work & productivity · No account needed · Local servers